Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2978 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1867. Min Act: -0.0000

Data Index: 244641 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1319588 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1112255 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1609. Min Act: -0.0000

Data Index: 906362 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1351115 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1575. Min Act: -0.0000

Data Index: 8806 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1661. Min Act: -0.0000

Data Index: 967222 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1451. Min Act: -0.0000

Data Index: 876185 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1480. Min Act: -0.0001

Data Index: 569051 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1442. Min Act: -0.0001

Data Index: 481114 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1517. Min Act: -0.0001

Data Index: 212523 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1518. Min Act: -0.0000

Data Index: 713339 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1436. Min Act: -0.0001

Data Index: 366492 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1480. Min Act: -0.0001

Data Index: 465223 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1463. Min Act: -0.0001

Data Index: 711533 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1350. Min Act: -0.0001

Data Index: 681524 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1396. Min Act: -0.0001

Data Index: 26374 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1130. Min Act: -0.0000

Data Index: 365787 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1362. Min Act: -0.0001

Data Index: 48038 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1381. Min Act: -0.0001

Data Index: 972255 (C4 (Web Text))

Max Activating Token Index: 302